// Open-model VRAM table · family
Xiaomi MiMo: local deployment & VRAM
14 open-weight models from Xiaomi (18 official repos incl. quantised builds). At 4-bit they range from 6.9 GB (MiMo-7B-Base) to 681 GB (MiMo-V2.6-Pro-MOPD).
official orgs: XiaomiMiMolatest 2026-09-27memory = estimate
01Text LLM (9)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| MiMo-V2.6-Flash-MOPD | 309B / 15B | 1M | 680 GB | 207 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB | Commercial OK | 2026-09-27 |
| MiMo-V2.6-Pro-MOPD | 1.02T / 42B | 1M | 2.24 TB | 681 GB | 8 × H200 (1,128GB) | — | Commercial OK | 2026-09-27 |
| MiMo-V2.6-Flash-RL | 309B / 15B | 1M | 680 GB | 207 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB | Commercial OK | 2026-09-21 |
| MiMo-V2.6-Pro-RL | 1.02T / 42B | 1M | 2.24 TB | 681 GB | 8 × H200 (1,128GB) | — | Commercial OK | 2026-09-21 |
| MiMo-V2.5 | 310B / 15B | 1M | 683 GB | 207 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB | Commercial OK | 2026-04-27 |
| MiMo-V2.5-Pro | 1.02T / 42B | 1M | 2.24 TB | 681 GB | 8 × H200 (1,128GB) | — | Commercial OK | 2026-04-27 |
| MiMo-V2-Flash | 309B / 15B | 256K | 680 GB | 207 GB | 4 × RTX PRO 6000 (384GB) | Mac 512GB | Commercial OK | 2025-12-16 |
| MiMo-7B-Base | 7.83B | 32K | 18.9 GB | 6.9 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-04-29 |
| MiMo-7B-RL | 7.83B | 32K | 18.9 GB | 6.9 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-04-29 |
02Vision-language (3)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| MiMo-V2.6-Distill-Qwen-9B | 9.41B | 256K | 21.5 GB | 7.0 GB | 8GB GPU | Mac 16GB | Commercial OK | 2026-09-21 |
| MiMo-VL-7B-RL-2508 ↗ | 8.31B | 125K | 20.0 GB | 7.2 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-08-07 |
| MiMo-VL-7B-RL ↗ | 8.31B | 125K | 20.0 GB | 7.2 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-05-30 |
03Omni / audio LLM (1)
| Model | Params | Context | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|---|
| MiMo-Audio-7B-Instruct ↗ | 8.02B | 8K | 19.4 GB | 7.1 GB | 8GB GPU | Mac 16GB | Commercial OK | 2025-09-18 |
04Speech-to-text (1)
| Model | Params | BF16 | 4-bit | Smallest GPU (4-bit) | Mac (4-bit) | Licence | Released |
|---|---|---|---|---|---|---|---|
| MiMo-V2.5-ASR ↗ | 7.62B | 17.3 GB | 5.6 GB | 8GB GPU | Mac 16GB | Commercial OK | 2026-04-23 |
05Other families
Qwen · IBM Granite · NVIDIA Nemotron · Gemma · Mistral / Magistral / Devstral · GLM / CogVideoX (Z.ai) · DeepSeek · Ai2 OLMo / Molmo · Ant Ling / Ring / Ming · Liquid LFM · MiniCPM / VoxCPM · Tencent Hunyuan / Hy · Phi · Llama · Meituan LongCat · Jina embeddings & rerankers · Wan · Kimi · Cohere Command / Aya · FLUX · Microsoft VibeVoice / Fara / Harrier · InternLM / Intern-S · StepFun Step · MiniMax · Baidu ERNIE · NVIDIA Parakeet / Canary speech · Stable Diffusion / Stable Audio · Yi (01.AI) · ByteDance Seed · SmolLM / SmolVLM · BGE embeddings & rerankers · LTX Video · FunAudioLLM speech · gpt-oss · poolside Laguna · Whisper · Baichuan · Thinking Machines Inkling · xAI Grok · rednote dots
Totals include 10% + 0.5GB overhead and one 8K-token KV cache for text models. Estimates only. Method →